Back
Year
2025
Tech Stack
R, RStudio, tidyverse, lubridate, R Markdown
Description
A county-level statistical analysis of COVID-19 case disparities
across the US from 2020–2022. Three data sources — Johns Hopkins case data,
Google Mobility, and county demographic and healthcare statistics — were merged
into a unified longitudinal dataset to examine how mobility patterns, age
structure, education levels, and healthcare capacity relate to differences in
case rates.
Why This Project Matters
Public health analysis can overlook differences between individual
counties when risk is treated uniformly. This project examines measurable
county-level factors associated with disparities in case rates, providing a
data-driven basis for understanding how mobility, demographics, education, and
healthcare capacity relate to uneven outcomes.
Technical Highlights
- Merged three data sources: Johns Hopkins case data, Google Mobility, and county demographic and healthcare statistics
- Built a unified longitudinal dataset spanning 2020–2022
- Developed a reproducible R Markdown statistical workflow for analysing case-rate predictors
- Examined four predictor domains: mobility, age structure, education, and healthcare capacity
Key Features
- County-level exploratory analysis
- County-level statistical analysis
- Multi-source longitudinal data integration
- Predictor analysis across four research domains
- Reproducible R Markdown report and visualisations
My Role
- 🧩 Worked as the sole developer across the analysis
- 📊 Merged the three source datasets into one longitudinal dataset
- 🧮 Built the R Markdown statistical analysis workflow
- 🔍 Ran predictor modelling across mobility, age, education, and healthcare capacity
- 📈 Built the reproducible report and visualisations and sourced and cleaned the county-level datasets